Schlagwort: voice recognition

  • Discover #Virgil: history comes to life with Arduino

    Discover #Virgil: history comes to life with Arduino

    Reading Time: 2 minutes

    We’re excited to introduce #Virgil, an innovative project that combines the power of Arduino technology with a passion for history, creating a groundbreaking interactive experience for museums. 

    Using Arduino’s versatile and scalable ecosystem, #Virgil operates completely offline, allowing visitors to interact with 3D avatars in a seamless and immersive way. The project brings the past to life, offering dialogue-driven encounters with key historical figures thanks to voice recognition and edge AI – with the option to choose among many different languages.

    “#Virgil is meant to celebrate the past and, more importantly, open new avenues for education and inspiration. We want to prove how technology, when guided by ethical values, can amplify and perpetuate our cultural heritage in ways that used to be unimaginable,” comments Enrico Benevenuta, coordinator of the Territori Svelati project and AI expert.

    [youtube https://www.youtube.com/watch?v=hQBPIePZDMs?feature=oembed&w=500&h=281]

    Matteo Olivetti, great-grandson of Olivetti’s founder Camillo, drew inspiration from the iconic Divisumma to design a dedicated hardware setup, Olivox. 

    Powered by the Portenta X8 and Max Carrier, the device connects via HDMI to any screen, engaging visitors in a rich, interactive experience without the need for smartphones or a stable internet connection. This approach allows the project to adapt easily to different exhibitions and contexts, while offering full control over the visitor experience.

    Internationally renowned 3D artist Elvis Morelli was entrusted with creating the first avatar of the project – and it’s no coincidence that Camillo Olivetti was chosen. 

    The story of Olivetti resonates deeply with Arduino’s own mission of pushing the boundaries of technology, and #Virgil represents a continuation of that legacy by bridging the gap between the past and future through cutting-edge tools.

    To find out more about the project and perhaps have a chat with your favorite pioneer of technology and innovation, visit #Virgil’s booth at the upcoming 2024 Maker Faire Rome, booth E.09. Don’t forget to stop by Arduino’s booth N.07 to find out more about our products, and let us know what you asked Camillo!

    The post Discover #Virgil: history comes to life with Arduino appeared first on Arduino Blog.

    Website: LINK

  • Controlling a power strip with a keyword spotting model and the Nicla Voice

    Controlling a power strip with a keyword spotting model and the Nicla Voice

    Reading Time: 2 minutes

    As Jallson Suryo discusses in his project, adding voice controls to our appliances typically involves an internet connection and a smart assistant device such as Amazon Alexa or Google Assistant. This means extra latency, security concerns, and increased expenses due to the additional hardware and bandwidth requirements. This is why he created a prototype based on an Arduino Nicla Voice that can provide power for up to four outlets using just a voice command.

    Suryo gathered a dataset by repeating the words “one,” “two,” “three,” “four,” “on,” and “off” into his phone and then uploaded the recordings to an Edge Impulse project. From here, he split the files into individual words before rebalancing his dataset to ensure each label was equally represented. The classifier model was trained for keyword spotting and used Syntiant NDP120-optimal settings for voice to yield an accuracy of around 80%.

    Apart from the Nicla Voice, Suryo incorporated a Pro Micro board to handle switching the bank of relays on or off. When the Nicla Voice detects the relay number, such as “one” or “three”, it then waits until the follow-up “on” or “off” keyword is detected. With both the number and state now known, it sends an I2C transmission to the accompanying Pro Micro which decodes the command and switches the correct relay.

    To see more about this voice-controlled power strip, be sure to check out Suryo’s Edge Impulse tutorial.

    [youtube https://www.youtube.com/watch?v=9PRjhA38jBE?feature=oembed&w=500&h=281]

    The post Controlling a power strip with a keyword spotting model and the Nicla Voice appeared first on Arduino Blog.

    Website: LINK

  • Fortune Cat uses embedded speech recognition to predict your future

    Fortune Cat uses embedded speech recognition to predict your future

    Reading Time: 2 minutes

    For well over one hundred years, people have been constructing machines that dispense fortunes to those who ask at the insertion of a coin and the push of a button. In modern days, this has taken the form of mobile apps that can be far more expansive, albeit with a lack of physical interaction. Seeing an opportunity to use an embedded speech recognition model in this kind of application, the Electronic Cats team built the aptly named Fortune Cat just in time for some Halloween fun.

    This small device, based on the Arduino Nano 33 BLE Sense, takes advantage of the onboard microphone to listen for words being spoken at the small cube. Performing the language processing is Cyberon’s Arduino Speech Recognition Engine, which was configured to listen for the wake phrase “Fortune Cat” and then later respond to “tell me my future” as its command phrase. After generating the model online, it was incorporated into the code via the DSpotter software development kit that lets the program check if either the wake or action phrase has been said and then act accordingly.

    In this case, asking Fortune Cat for your future will present one of 20 random phrases that get displayed on the OLED mounted to the top of the 3D-printed enclosure. To read more about how the Electronic Cats crew created and configured Fortune Cat, you can check out their write-up here on Hackster.io or watch their video below!

    [youtube https://www.youtube.com/watch?v=KrPEl2D1z5E?feature=oembed&w=500&h=281]

    The post Fortune Cat uses embedded speech recognition to predict your future appeared first on Arduino Blog.

    Website: LINK

  • This smartlock uses voice recognition to control access

    This smartlock uses voice recognition to control access

    Reading Time: 2 minutes

    A Smartlock are a highly convenient way to secure a house, and they can have their number of connectivity options expanded even further by connecting them to an IoT home assistant service such as Google Assistant or Amazon Alexa.

    Arduino Team — July 16th, 2022

    Jithin Sanal’s project uses Amazon’s Alexa skill to automatically secure a custom door locking mechanism without the need for Bluetooth or a fingerprint.

     

     It is based around a Nano RP2040 Connect, and due to its onboard connectivity suite, can talk with the Arduino Cloud.

     

    Other than the Nano, Sanal designed a simple PCB. With pads for a buzzer, voltage regulator, and several LEDs for monitoring.

    The circuit also includes a relay that applies power to a solenoid.
    Which acts as a deadbolt when power is applied.

    After receiving the bare PCB and soldering each component onto it, Sanal moved onto writing the code for his creation. In simple terms, the Arduino Cloud project contains a single variable for getting/setting the value of the lock.

    [youtube https://www.youtube.com/watch?v=QE4WQh3YQWs?feature=oembed&w=500&h=281]

    A method is called in the fw that sets the solenoid to this new state and makes a few beeps with the buzzer.

     

    Associating the Arduino Alexa skill with the IoT device, thus letting someone set the lock as a dedicated Smartlock device.

    You can see more details on this project in Sanal’s Hackster.io write-up.

    You can follow any responses to this entry through the RSS 2.0 feed.
    You can leave a response, or trackback from your own site.

    Website: LINK

  • Build your own adorable, talking WALL-E robot

    Build your own adorable, talking WALL-E robot

    Reading Time: 2 minutes

    Arduino Team — July 3rd, 2021

    Film history is full of cute robots, but for our money, none are more charming than WALL-E. His vocabulary may be limited, but that doesn’t stop him from showing the full range of emotions through body language. Like Baby Yoda, WALL-E was an instant fan-favorite and a plethora of toys were made in his honor. If you can get your hands on one, Kevr102 has an Instructables tutorial that will walk you through how to bring that toy to life with the help of an Arduino.

    To complete this project exactly as Kevr102 describes, you will need a specific 7″ tall plastic WALL-E toy. That toy has motors for the tracks, arm movement, and head movement. Starting with that will save you the trouble of mechanical design and 3D printing work. But you will replace all of the motors to make them easier to control. In total, you will need two 360 degree servo motors, three heavy duty servo motors, and two micro servo motors.

    You will control those motors with an Arduino Nano through a servo shield. The exciting part of the build, which enables your WALL-E robot to respond to voice commands, works thanks to an EasyVR3 voice recognition module. That module also lets you play sounds, so WALL-E can emit his signature sound effects and modulated voice. Kevr102 explains how you can setup custom voice commands and sound effects, so you can tailor them to suit your tastes.

    [youtube https://www.youtube.com/watch?v=7lZXOYiSeek?start=1&feature=oembed&w=500&h=281]

    [youtube https://www.youtube.com/watch?v=ukP5Eq2CP5M?feature=oembed&w=500&h=281]

    You can follow any responses to this entry through the RSS 2.0 feed.
    You can leave a response, or trackback from your own site.

    Website: LINK

  • Raspberry Pi ‘Swear Bear’ keeps your potty mouth in check

    Raspberry Pi ‘Swear Bear’ keeps your potty mouth in check

    Reading Time: 2 minutes

    Why use a regular swear jar to retrain your potty-mouthed brain when you can build a Swear Bear to help you instead?

    Swear Bear listens to you. All the time. And Swear Bear can tell when a swear word is used. Swear Bear tells you off and saves all the swear words you said to the cloud to shame you. Swear Bear subscribes to the school of tough love.

    [youtube https://www.youtube.com/watch?v=ASSAGECmZt4?feature=oembed&w=500&h=281]

    Artificial intelligence

    The Google AIY kit allows you to build your own natural language recogniser. This page shows you how to assemble the Voice HAT from the kit, and it also includes the code you’ll need to make your project capable of speech-to-text AI.

    To teach Swear Bear the art of profanity detection, Swear Bear creators 8 Bits and a Byte turned to the profanity check Python library. You can find the info to install and use the library on this page, as well as info on how it works and why it’s so accurate.

    You’ll hear at this point in the video that Swear Bear says “Oh dear” when a swear word is used within earshot.

    Hardware

    Birds eye view of each of the hardware components used in the project on a green table

    This project uses the the first version of Google’s AIY Voice Kit, which comes with a larger black AIY Voice HAT and is compatible with Raspberry Pi 3 Model B. The kit also includes a little Voice HAT microphone board.

    Version 2 of the kit comprises the smaller Raspberry Pi Zero WH and a slimmer ‘Voice Bonnet’.

    The microphone allows Swear Bear to ‘hear’ your speech, and through its speakers it can then tell you off for swearing.

    All of hardware is squeezed into the stuffing-free bear once the text-to-speech and profanity detection software is working.

    Babbage Bear hack?

    Babbage the Bear

    8 Bits and a Byte fan Ben Scarboro took to the comments on YouTube to suggest they rework one of our Babbage Bears into a Swear Bear. Babbage is teeny tiny, so maybe you would need to fashion a giant version to accomplish this. Just don’t make us watch while you pull out its stuffing.

    Website: LINK

  • Watch Game of Thrones with a Raspberry Pi-powered Drogon

    Watch Game of Thrones with a Raspberry Pi-powered Drogon

    Reading Time: 2 minutes

    Channel your inner Targaryen by building this voice-activated, colour-changing, 3D-printed Drogon before watching the next episode of Game of Thrones.

    Winter has come

    This is a spoiler-free zone! I’ve already seen the new episode of season 8, but I won’t ruin anything, I promise.

    Even if you’ve never watched an episode of Game of Thrones (if so, that’s fine, I don’t judge you), you’re probably aware that the final season has started.

    And you might also know that the show has dragons in it — big, hulking, scaley dragons called Rhaegal, Viserion, and Drogon. They look a little something like this:Daenerys-Targaryen-game-of-thrones

    Well, not anymore. They look like this now:

    04_15_GameOfThrones_S07-920x584

    Raspberry Pi voice-responsive dragon!

    The creator of this project goes by the moniker Botmation. To begin with, they 3D printed modified a Drogon model they found on Thingiverse. Then, with Dremel in hand, they modified the print, to replace its eyes with RGB LEDs. Before drawing the LEDs through the hollowed-out body of the model, they soldered them to wires connected to a Raspberry Pi Zero W‘s GPIO pins.

    Located in the tin beneath Drogon, the Pi Zero W is also equipped with a microphone and runs the Python code for the project. And thanks to Google’s Speech to Text API, Drogon’s eyes change colour whenever a GoT character repeats one of two keywords: white turns the eyes blue, while fire turns them red.

    If you’d like more information about building your own interactive Drogon, here’s a handy video. At the end, Botmation asks viewers to help improve their code for a cleaner voice-activation experience.

    3D printed Drogon with LED eyes for Game of Thrones

    Going into the final season of Game of Thrones with your very own 3D printed Drogron dragon! The eyes are made of LEDs that changes between Red and Blue depending on what happens in the show. When you’re watching the show, Drogon will watch the show with you and listen for cues to change the eye color.

    Drogon for the throne!

    I’ve managed to bag two of the three dragons in the Pi Towers Game of Thrones fantasy league, so I reckon my chances of winning are pretty good thanks to all the points I’ll rack up by killing White Walker.

    Wait — does killing a White Walker count as a kill, since they’re already dead?

    Ah, crud.

    Website: LINK